import re
import nltk
from nltk.tokenize import sent_tokenize, word_tokenize
dir = 'Corpus'
titles = []
sentenceLength = []
for file in os.listdir( dir ):
if re.search( r'[.]txt' , file ):
fullPath = join( dir , file )
print( 'Analysing ' + fullPath + '...' )
tokens = tdm.numberOfTokens( fullPath )
sentences = tdm.numberOfSentences( fullPath )
sentenceLength.append( tokens / sentences )
title = re.sub( r'\.txt' , '' , file )
titles.append( title )
import matplotlib.pyplot as plt
fig = plt.figure( figsize=( 12 , 5 ) )
ax = plt.axes()
ax.bar( titles , sentenceLength , width = 0.6 , alpha = 0.5 , color = '#03017a')
import re
import os
from os.path import join
import dtdpTdm as dtdp
out = open('data.csv', 'w')
dir = 'Corpus'
## make a heade
out.write('title,tokens,sentences,syllables\n')
for file in os.listdir(dir):
if re.search(r'[.]txt', file):
fileName = join(dir, file)
print("Analysing " + fileName + " ...")
out.write(fileName + ',')
print("Calculating number of tokens")
out.write(str(dtdp.numberOfTokens(fileName)))
out.write(',')
print("Calculating number of sentences")
out.write(str(dtdp.numberOfSentences(fileName)))
out.write(',')
print("Calculating number of syllables")
out.write(str(dtdp.numberOfSyllables(fileName)))
out.write('\n')
out.close()